OPTIMIZING MEDICAL IMAGING NANOTECHNOLOGY AND INDUSTRIAL ROBOTICS THROUGH MACHINE LEARNING IMPLEMENTATION

Abstract

This thesis looks at the ability of machine learning algorithms to improve the functionality of automation systems across two diverse but significant fields: industrial robotics and medical nanotechnology. The first project entails developing machine learning algorithms for a vision system for industrial robots, allowing them to learn from previous experiences and adapt to changing settings. The suggested approach is specifically used to MCC panel inspections at TATA Steel Kalinganar, and the results show considerable improvements in the system’s accuracy and speed. The second project investigates the application of machine learning algorithms in biomedical nanotechnology as a tool for identifying disorders such as fatty liver disease. For fatty liver disease identification, multi-parametric ultrasound imaging and reconstruction approaches based on deep learning technology are being developed. Using in-vivo ultrasound data, the new technology is proven to attain great accuracy and reliability when compared to previous methods. The overarching purpose of this thesis is to provide strategies that can increase the precision, dependability, and speed of automation systems across industrial robotics and medical nanotechnology, therefore contributing to the growth of both areas. The findings of this study might open up possibilities for smarter and effective automation solutions in various domains, ultimately leading to improved healthcare.